We launched Vaccine Information Resource Assistant (VIRA) to support informed decision-making for young people by providing them with 24/7 access to reliable information in a format that is engaging, empathic, and accessible. We call the chatbot VIRA for short.
The chatbot “VIRA” can only look up questions in the database of messages approved by Johns Hopkins vaccine scientists. VIRA cannot write a new response.
While we hope VIRA can help people get answers to questions about COVID-19 vaccines from anywhere in the world, VIRA knows more about vaccines used in the United States at this time.
The Johns Hopkins team will be regularly refreshing the knowledge database VIRA draws from. Let us know how we can improve: feedback form.
IBM researchers are working on this project with the JHU team since December 2020, analyzing common concerns and queries related to the vaccines, and different ways in which people express them. The system is designed to continually learn from new conversations, by detecting emerging concerns and learn new ways in which people express existing ones.
VIRA the chatbot is made up of several components. Together, these functions enable VIRA to 'understand' the user's concern and respond with the most relevant answer in its database. VIRA's knowledge base covers over 150 distinct concerns, referred to as Key Points, which were expressed by real world users, and responses from vaccine scientists and public health specialists from Johns Hopkins. VIRA can recognize the many thousands of ways different people can express these key points, and it learns and improves based on your feedback.
The system does not generate texts on its own. Rather, all the information conveyed by the system has been curated and reviewed by experts in the field from Johns Hopkins University. Moreover, the team is working to continually update this information, according to latest data and guidelines.
One of the technologies is Key Point Analysis, one of the commercially available AI technologies developed by the Project Debater team. Key Point Analysis is the next generation of “extractive summarization,” used to process numerous comments, opinions and statements to reveal the most significant points and their relative prevalence.
The backend conversation engine is hosted on IBM Cloud. The user interface and website are hosted by Johns Hopkins University.
The decision to receive or not receive a vaccination is a personal one based on local government policies and individual rights and freedoms.
We envision developing similar chatbots to help individuals make more informed decisions about various topics such as quitting smoking, donating blood, voting and more.
Since 2014, the IBM Project Debater team has released more than 50 technical papers and associated benchmark datasets across multiple research domains, with several more publications pending. Some of the recent publications explain the Key Point Analysis technology and its potential applications. The following resources highlight the scientific advances that drive many of Project Debater's capabilities. They can be accessed here: https://www.research.ibm.com/artificial-intelligence/project-debater/research/. Key Point Analysis is available freely for academic use.
No, users are not required to register. The system collects the questions being asked and the feedback to the system response, to further improve the system, but this is 100% anonymous.